Loading packages for the plots
library(ggplot2)
library(plotly)
library(flexdashboard)
library(dplyr)
## Warning: package 'dplyr' was built under R version 4.1.3
library(tidyverse)
## Warning: package 'tidyverse' was built under R version 4.1.3
## Warning: package 'tibble' was built under R version 4.1.3
## Warning: package 'tidyr' was built under R version 4.1.3
## Warning: package 'readr' was built under R version 4.1.3
## Warning: package 'purrr' was built under R version 4.1.3
## Warning: package 'stringr' was built under R version 4.1.3
## Warning: package 'forcats' was built under R version 4.1.3
## Warning: package 'lubridate' was built under R version 4.1.3
library(leaflet)
Reading in Cleaned Data
alcohol_data_2007 = read_csv("./data/PRAM_2007_alcohol.csv")
tobacco_data_2007 = read_csv("./data/PRAM_2007_tobacco.csv")
no_contraception_data_2007 = read_csv("./data/PRAM_2007_no_contraception.csv")
infant_mortality_df = read_csv("./data/PRAM_2007_infantmortality.csv")
# cleaned alcohol data
cleaned_alc_2007 <- alcohol_data_2007 |>
janitor::clean_names() |>
select(-data_value_std_err, -data_value_type) |>
filter(response != "DRINKER WHO QUIT") |>
filter(response != "NONDRINKER") |>
filter( response != "NO") |>
drop_na(response,geolocation) |>
separate(geolocation, into = c("latitude", "longitude"), sep = ", ", convert = TRUE) |>
mutate(latitude = as.numeric(str_replace_all(latitude, "\\(|\\)", "")), # Convert to numeric and remove parentheses
longitude = as.numeric(str_replace_all(longitude, "\\(|\\)", ""))) # Convert to numeric and remove parentheses
# cleaned tobacco data
cleaned_tobac_2007 <- tobacco_data_2007 |>
janitor::clean_names() |>
select(-data_value_type) |>
filter(response != "SMOKER WHO QUIT") |>
filter(response != "NONSMOKER") |>
filter(response != "None (0 cig)") |>
filter( response != "NO") |>
drop_na(response, geolocation) |>
separate(geolocation, into = c("latitude", "longitude"), sep = ", ", convert = TRUE) |>
mutate(latitude = as.numeric(str_replace_all(latitude, "\\(|\\)", "")), # Convert to numeric and remove parentheses
longitude = as.numeric(str_replace_all(longitude, "\\(|\\)", ""))) # Convert to numeric and remove parentheses
no_alcohol_data_2007 = read_csv("./data/PRAM_2007_no_alcohol.csv")
no_tobacco_data_2007 = read_csv("./data/PRAM_2007_no_tobacco.csv")
contraception_data_2007 = read_csv("./data/PRAM_2007_contraception.csv")
# cleaned no alcohol data
cleaned_no_alc_2007 <- no_alcohol_data_2007 |>
janitor::clean_names() |>
select(-data_value_std_err, -geolocation, -data_value_type) |>
drop_na(response)
view(cleaned_no_alc_2007)
# cleaned no tobacco data
cleaned_no_tobacco_2007 <- no_tobacco_data_2007 |>
janitor::clean_names() |>
select(-data_value_std_err, -geolocation, -data_value_type) |>
drop_na(response)
# cleaned infant mortality
cleaned_infant_mortality <- infant_mortality_df |>
janitor::clean_names() |>
select(-data_value_std_err, -data_value_type, -data_value_unit, -data_value_footnote_symbol, -data_value_footnote) |>
drop_na(response, geolocation) |>
separate(geolocation, into = c("latitude", "longitude"), sep = ", ", convert = TRUE) |>
mutate(latitude = as.numeric(str_replace_all(latitude, "\\(|\\)", "")), # Convert to numeric and remove parentheses
longitude = as.numeric(str_replace_all(longitude, "\\(|\\)", ""))) # Convert to numeric and remove parentheses
# cleaned conception
cleaned_contraception_2007 <- contraception_data_2007 |>
janitor::clean_names() |>
select(-data_value_std_err, -geolocation, -data_value_type) |>
filter(response != "YES (CHECKED)") |>
filter(response != "YES") |>
drop_na(response)
# cleaned non conception
cleaned_no_contra_2007 <- no_contraception_data_2007 %>%
janitor::clean_names() %>%
select(-data_value_type) %>%
drop_na(response) |>
separate(geolocation, into = c("latitude", "longitude"), sep = ", ", convert = TRUE) |>
mutate(latitude = as.numeric(str_replace_all(latitude, "\\(|\\)", "")), # Convert to numeric and remove parentheses
longitude = as.numeric(str_replace_all(longitude, "\\(|\\)", ""))) # Convert to numeric and remove parentheses
Plot 1: Alcohol Consumption in relation to Infant Mortality
cleaned_infant_mortality <- infant_mortality_df |>
janitor::clean_names() |>
select(-data_value_std_err, -data_value_type, -data_value_unit, -data_value_footnote_symbol, -data_value_footnote) |>
drop_na(response)
# Plot of question and responses for alcohol
cleaned_alc_2007 |>
ggplot(aes(x = question, fill = response)) +
geom_bar(position = "dodge") +
labs(title = "Questions and Responses", x = "Questions", y = "Count") +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1))+
labs(
x = "Question",
y = "Response",
title = "Questions vs Response of Alcohol Consumption"
)

# creating "yes" variable
# plot showing infant mortality rate vs alcohol consumption
ggplot() +
geom_point(data = cleaned_alc_2007, aes(x = question, y = response), color = "blue", size = 3) +
geom_point(data = cleaned_infant_mortality, aes(x = question, y = response), color = "red", size = 3) +
labs(title = "Scatter Plot of Two Variables from Different Datasets",
x = "X-axis Label",
y = "Y-axis Label") +
theme_minimal()

Plot 2: Tobacco Consumption in relation to Infant Mortality
Plot 3: No Consumption in relation to Infant Mortality
leaflet() |>
addTiles() |>
addCircleMarkers(data = cleaned_alc_2007,
lng = ~longitude, # Adjust column name if needed
lat = ~latitude, # Adjust column name if needed
label = ~location_abbr, # Assuming 'Group.1' is a column in your data
radius = 7,
color = "orange",
stroke = TRUE,
fillOpacity = 0.75,
popup = ~paste("Response:", response))
<<<<<<< HEAD
<<<<<<< HEAD
=======
<<<<<<< HEAD
=======
>>>>>>> 94e7f9778c789b861d08491901c0e1020c6aa653
>>>>>>> 87eda6801483a374e516ba8f783995c3d11f822b
=======
>>>>>>> d62d042cf80b91ce83fdee3be5c3dcaae96e5cba
leaflet() |>
addTiles() |>
addCircleMarkers(data = cleaned_tobac_2007,
lng = ~longitude, # Adjust column name if needed
lat = ~latitude, # Adjust column name if needed
label = ~location_abbr, # Assuming 'Group.1' is a column in your data
radius = 7,
color = "orange",
stroke = TRUE,
fillOpacity = 0.75,
popup = ~paste("Response:", response))
<<<<<<< HEAD
<<<<<<< HEAD
=======
<<<<<<< HEAD
## Warning in validateCoords(lng, lat, funcName): Data contains 1 rows with either
## missing or invalid lat/lon values and will be ignored
=======
>>>>>>> 94e7f9778c789b861d08491901c0e1020c6aa653
>>>>>>> 87eda6801483a374e516ba8f783995c3d11f822b
=======
>>>>>>> d62d042cf80b91ce83fdee3be5c3dcaae96e5cba